{"total":24,"rows":[{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137,"area":null},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2108.12630","title":"GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer","created":"2021-08-28","cited_by_count":54,"area":null},{"id":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2205.15361","title":"TubeFormer-DeepLab: Video Mask Transformer","created":"2022-05-30","cited_by_count":35,"area":null},{"id":"2208.06974","title":"Learning Semantic Correspondence with Sparse Annotations","created":"2022-08-15","cited_by_count":31,"area":null},{"id":"2303.08685","title":"Making Vision Transformers Efficient from A Token Sparsification View","created":"2023-03-15","cited_by_count":29,"area":null},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27,"area":null},{"id":"2207.06095","title":"Eliminating Gradient Conflict in Reference-based Line-Art Colorization","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2112.04863","title":"3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis","created":"2021-12-09","cited_by_count":23,"area":null},{"id":"2107.10234","title":"Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks","created":"2021-07-21","cited_by_count":19,"area":null},{"id":"2105.03186","title":"A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2108.03662","title":"Discriminative Latent Semantic Graph for Video Captioning","created":"2021-08-08","cited_by_count":7,"area":null},{"id":"2107.02859","title":"Poly-NL: Linear Complexity Non-local Layers with Polynomials","created":"2021-07-06","cited_by_count":5,"area":null},{"id":"2212.10207","title":"Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2106.03162","title":"Transformed ROIs for Capturing Visual Transformations in Videos","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2212.03338","title":"Framework-agnostic Semantically-aware Global Reasoning for Segmentation","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2102.07997","title":"A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images","created":"2021-02-16","cited_by_count":0,"area":null},{"id":"2210.05676","title":"Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2301.02747","title":"Sample-efficient Surrogate Model for Frequency Response of Linear PDEs using Self-Attentive Complex Polynomials","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2305.14880","title":"Multiresolution Feature Guidance Based Transformer for Anomaly Detection","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2501.03045","title":"Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments","created":"2025-01-06","cited_by_count":0,"area":null}],"next_cursor":null}